• Smruthi K R
• Medha Shree
• Dr Mallikarjun H M

Financial fraud detection has become increasingly critical due to the rapid rise in online financial transactions and cyber threats. Machine Learning (ML) algorithms offer promising solutions by identifying suspicious patterns from large-scale transactional data. This study compares the performance of eight supervised ML models— Logistic Regression (L1 and L2), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree, Random Forest, Naive Bayes, and XGBoost—on a real-world credit card fraud dataset. Models were evaluated based on Accuracy, Precision, Recall, and ROC-AUC. Results reveal that XGBoost and Random Forest outperformed others in overall performance, while Logistic Regression (L1) exhibited high recall but low precision. The findings provide practical insights for deploying ML-based fraud detection systems in financial institution

"Performance Comparison of ML Algorithms in Detecting Financial Fraud", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.h741-h748, May-2025, Available :http://www.jetir.org/papers/JETIR2505876.pdf

"Performance Comparison of ML Algorithms in Detecting Financial Fraud", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. pph741-h748, May-2025, Available at : http://www.jetir.org/papers/JETIR2505876.pdf